Proceedings of the
The Nineteenth International Conference on Computational Intelligence and Security (CIS 2023)
December 1 – 4, 2023, Haikou, China
Firefly Evolutionary Algorithm Based on Decomposition for Many-Objective Optimization
School of Computer Science, Shaanxi Normal University, China.
ABSTRACT
Firefly algorithm (FA) has the advantages of a simple structure and good search ability, but it has the disadvantages of being prone to falling into local optima and having a high dependence on excellent individuals, which leads to poor performance in solving many-objective optimization problems (MaOPs). In order to address these issues, this paper proposes a firefly evolutionary algorithm based on decomposition (FEA/D). The main goal of this paper is to produce good offspring through an update strategy and selection strategy to balance convergence and diversity. Specifically, the update strategy is used to explore the global optimal solution, while the selection strategy is employed to choose high-quality parents, thereby enhancing the local search. In addition, a new decomposition strategy is used to maintain diversity. FEA/D is compared with several other state-of-the-art algorithms on the many-objective benchmark functions. The experimental results verify the effectiveness of the proposed algorithm. Keywords: Many-objective optimization, Firefly optimization, Decomposition, Evolutionary algorithm, Diversity, Archive.
Download PDF
School of Computer Science, Shaanxi Normal University, China.
ABSTRACT
Firefly algorithm (FA) has the advantages of a simple structure and good search ability, but it has the disadvantages of being prone to falling into local optima and having a high dependence on excellent individuals, which leads to poor performance in solving many-objective optimization problems (MaOPs). In order to address these issues, this paper proposes a firefly evolutionary algorithm based on decomposition (FEA/D). The main goal of this paper is to produce good offspring through an update strategy and selection strategy to balance convergence and diversity. Specifically, the update strategy is used to explore the global optimal solution, while the selection strategy is employed to choose high-quality parents, thereby enhancing the local search. In addition, a new decomposition strategy is used to maintain diversity. FEA/D is compared with several other state-of-the-art algorithms on the many-objective benchmark functions. The experimental results verify the effectiveness of the proposed algorithm. Keywords: Many-objective optimization, Firefly optimization, Decomposition, Evolutionary algorithm, Diversity, Archive.
Download PDF